KR20230010164A - Method and apparatus for calculating fat mass using images of head and neck - Google Patents

Abstract

The present invention relates to a fat mass calculation method and a device for the same. A fat mass calculation method according to an embodiment of the present invention comprises the steps of: acquiring an image group including a plurality of two-dimensional images generated in correspondence to the continuous volume of the head and neck of a user; inputting the image group to a first trained network function so as to generate first image information in which at least a portion of a brain area has been removed from the image group; inputting the first image information to a trained second network function so as to generate second image information in which a fat area has been detected in the first image information; and calculating the fat mass in the head and neck from the second image information. The present invention can quickly and accurately detect fat areas from head and neck MR images using a neural network and calculate the fat mass.

Description

Fat mass calculation method using head and neck video images and device therefor

The technical idea of the present disclosure relates to a fat amount calculation method using head and neck video images and an apparatus therefor.

Among the methods used to measure body composition, there are a bioelectrical impedance method (BIA) and a bone density measurement method (DEXA). The bioelectrical impedance method is a method of measuring a resistance value after flowing a microcurrent through the body, and has a disadvantage in that the accuracy is low and the measured value varies greatly depending on the subject's water intake. In addition, the bone density measurement method is a method of measuring the transmittance through which radiation penetrates the human body, and there is a risk of exposure when imaging frequently due to radiation. Therefore, a technology for more safely and accurately measuring body composition is required.

A fat mass calculation method and apparatus for calculating fat mass according to the technical idea of the present disclosure are to accurately and quickly detect a fat region from an MR image, and calculate a fat mass in the head and neck region from the fat mass calculation method and apparatus therefor is to provide

The technical task to be achieved by the method for calculating fat mass and the device therefor according to the technical spirit of the present disclosure is not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below. .

According to one aspect of the technical idea of the present disclosure, a fat mass calculation method includes obtaining an image group including a plurality of two-dimensional images generated corresponding to the continuous volume of the head and neck of a user; generating first image information in which at least a part of a brain region is removed from the image group by inputting the image group to a first learned network function; generating second image information obtained by detecting a fat region from the first image information by inputting the first image information to a learned second network function; and calculating the amount of fat in the head and neck from the second image information.

According to an exemplary embodiment, the head and neck portion may include a region from the head of the user to a second cervical vertebra of the neck.

According to an exemplary embodiment, the generating of the first image information may be performed by removing a white matter region from among the brain regions.

According to an exemplary embodiment, the method may further include generating third image information including the fat region based on the first image information and the second image information.

According to an exemplary embodiment, the method may further include estimating the amount of fat in the entire body from the amount of fat.

According to an exemplary embodiment, the method may further include estimating a disease risk of the user from the amount of fat.

According to an exemplary embodiment, the step of predicting the disease risk may include at least one of abdominal fat, sarcopenia, dyslipidemia, diabetes, and hyperuricemia. It can be performed by predicting the degree of risk for

According to an exemplary embodiment, the method may further include obtaining body information of the user, wherein the body information may include height, weight, and past medical history of the user.

According to one aspect of the technical concept of the present disclosure, a fat mass calculating device includes a memory for storing a program for calculating fat mass; And by executing the program, an image group including a plurality of two-dimensional images generated corresponding to the continuous volume of the user's head and neck is obtained, and the image group is input to the learned first network function to obtain information from the image group. First image information from which at least a part of the brain region is removed is generated, and the first image information is input to the learned second network function to obtain second image information obtained by detecting a fat region from the first image information. and at least one processor configured to calculate the amount of fat in the head and neck region from the second image information.

According to one aspect of the technical concept of the present disclosure, a computer program stored in a recording medium may be provided to execute a fat mass calculation method.

According to the fat mass calculation device and the device therefor according to embodiments according to the technical concept of the present disclosure, it is possible to quickly and accurately detect an ice area from a head and neck MR image and calculate fat mass using a neural network.

Effects that can be obtained by the fat mass calculating device and the device therefor according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned are common in the art to which the present disclosure belongs from the description below. It will be clearly understood by those who have knowledge.

A brief description of each figure is provided in order to more fully understand the figures cited in this disclosure.
1 is a flowchart illustrating a fat mass calculation method according to an embodiment of the present disclosure.
Figure 2 is a view for explaining the head and neck according to an embodiment of the present disclosure.
3 is an exemplary diagram of image information generated through a fat mass calculation method according to an embodiment of the present disclosure.
4 is an exemplary diagram of image information generated through a fat mass calculation method according to an embodiment of the present disclosure.
5 is an exemplary view of a disease risk predicted based on a fat mass calculation result according to an embodiment of the present disclosure.
6 is a block diagram briefly illustrating the configuration of a fat mass calculating device according to an embodiment of the present disclosure.

Since the technical spirit of the present disclosure may be subject to various changes and may have various embodiments, specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the technical spirit of the present disclosure to specific embodiments, and should be understood to include all changes, equivalents, or substitutes included in the scope of the technical spirit of the present disclosure.

In describing the technical idea of the present disclosure, if it is determined that a detailed description of a related known technology may unnecessarily obscure the subject matter of the present disclosure, the detailed description will be omitted. In addition, numbers (eg, first, second, etc.) used in the description process of the present disclosure are only identifiers for distinguishing one component from another component.

In addition, in the present disclosure, when one component is referred to as "connected" or "connected" to another component, the one component may be directly connected or directly connected to the other component, but in particular Unless otherwise described, it should be understood that they may be connected or connected via another component in the middle.

In addition, terms such as "~ unit", "~ group", "~ character", and "~ module" described in the present disclosure mean a unit that processes at least one function or operation, which includes a processor, a micro Processor (Micro Processor), Micro Controller, CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerate Processor Unit), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) may be implemented by hardware or software or a combination of hardware and software.

In addition, it is intended to make it clear that the classification of components in the present disclosure is merely a classification for each main function in charge of each component. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each component to be described below may additionally perform some or all of the functions of other components in addition to its main function, and some of the main functions of each component may be performed by other components. Of course, it may be dedicated and performed by .

Hereinafter, embodiments of the present disclosure will be described in detail in turn.

Throughout this specification, network function may be used interchangeably with neural network and/or neural network. Here, a neural network (neural network) may be composed of a set of interconnected computational units, which may be generally referred to as nodes, and these nodes may be referred to as neurons. A neural network is generally composed of a plurality of nodes. Nodes constituting a neural network may be interconnected by one or more links.

Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers.

The neural network described herein may include a deep neural network (DNN) including a plurality of hidden layers in addition to an input layer and an output layer.

1 is a flowchart illustrating a fat mass calculation method according to an embodiment of the present disclosure.

The fat mass calculation method 100 according to an embodiment of the present disclosure may be performed in a personal computer equipped with arithmetic capability, a workstation, a computer device for a server, or a separate device for this purpose.

Also, the fat mass calculation method 100 may be performed in one or more computing devices. For example, at least one or more steps of the method 100 for calculating fat mass according to an embodiment of the present disclosure may be performed by a client device and other steps may be performed by a server device. In this case, the client device and the server device may be connected through a network to transmit and receive calculation results. Alternatively, the fat mass calculation method 100 may be performed by distributed computing technology.

In step S110, the fat mass calculating device may acquire an image group including a plurality of 2D images generated corresponding to the continuous volume of the head and neck region. For example, the image group may be MR imaging images of the subject's head and neck. That is, the plurality of 2D images constituting the image group may be a plurality of slices obtained by sequentially photographing cross-sections of the head and neck in one direction through a magnetic resonance imaging method. By stacking these two-dimensional images, it is possible to obtain three-dimensional image information on the head and neck. In addition, the head and neck region may include a region from the head of the user to the second cervical vertebra in the neck region.

In operation S120 , the fat mass calculation device may input the image group to the learned first network function to generate first image information in which at least a part of a brain region is removed from the image group. The first network function may be one in which brain region segmentation has been previously learned through training data (eg, brain region MR images in which brain region extraction and/or separation has been performed by an expert).

In an embodiment, step S120 may be performed by removing a white matter region from among brain regions.

In operation S130 , the fat mass calculation device may input the first image information to the learned second network function to generate second image information obtained by detecting a fat region from the first image information. The second network function may be one in which fat region detection has been previously learned through learning data (eg, a head and neck MR image in which fat region detection has been performed by an expert).

In an embodiment, the second image information may be another 2D image obtained by masking a fat region in a plurality of 2D images, or data including coordinate information on the fat region.

In an embodiment, the first network function and the second network function may be generated by the same or different learning models.

In step S140 , the fat amount calculating device may calculate the amount of fat in the head and neck from the second image information. For example, step S140 may include calculating an area of a fat region in each 2D image in the second image information; and calculating a fat amount by summing up the areas of each 2D image. Also, for example, step S140 may be performed by calculating the amount of fat based on the number of pixels corresponding to the fat area and the volume per pixel in the second image information. However, it is not limited thereto.

In an embodiment, the fat mass calculating device may generate third image information including a fat region based on the first image information and the second image information. The third image information may include a plurality of 2D images and/or a 3D image generated by combining them. The third image information may be displayed to users, medical staff, and other experts. For example, the third image information may be displayed by overlapping a head and neck image generated based on the first image information with a fat region generated based on the second image information. The fat region and other regions may be displayed with different colors and/or different transparency.

In an embodiment, the fat mass calculation device may acquire user's body information. At this time, the body information may include at least one of the user's height, weight, and past medical history. The body information may be used together with the fat mass in step S140 or independently to predict the fat mass, muscle mass, disease risk, and the like of the user's entire body.

In an embodiment, the fat amount calculating device may predict the fat amount of the entire body from the fat amount. At this time, the user's body information may be considered together, but is not limited thereto.

In an embodiment, the fat mass calculation device may predict the disease risk from the fat mass in step S140. At this time, the user's body information may be considered together, but is not limited thereto. The disease risk may include a risk for at least one of abdominal fat, sarcopenia, dyslipidemia, diabetes, and hyperuricemia. However, these diseases are exemplary and can be used to predict the risk of various diseases that have a correlation with fat mass.

Figure 2 is a view for explaining the head and neck according to an embodiment of the present disclosure.

The fat mass calculation device may acquire an image group including a plurality of 2D images generated corresponding to the continuous volume of the head and neck region, and calculate the fat mass based on the obtained image group.

In this case, the head and neck includes the head and the neck, and more specifically, as shown in FIG. 2 , it may include a region from the head to the second cervical vertebra (axis, C2) of the neck.

In addition, since the angle of the head is different depending on the user when capturing the image group, the image group captured for the region including the mandible, that is, the region above the red line, can be used in consideration of this.

The target region of the image group shown in FIG. 2 is an example, and image groups for various regions may be used according to an embodiment of the present disclosure.

3 is an exemplary diagram of image information generated through a fat mass calculation method according to an embodiment of the present disclosure.

Referring to (a) of FIG. 3 , some of the image groups for the head and neck are shown. The image group may include a plurality of 2D images generated corresponding to the continuous volume of the head and neck, and thus each 2D image may be displayed and/or a 3D image generated by combining them may be displayed.

Referring to (b) of FIG. 3, first image information generated by the first network function is shown. The first image information is obtained by removing a brain region from the image group, and may include a plurality of 2D images and/or a 3D image generated by combining them.

The image information shown in FIG. 3 is exemplary, and various image information may be used according to an embodiment of the present disclosure.

4 is an exemplary diagram of image information generated through a fat mass calculation method according to an embodiment of the present disclosure.

Referring to FIG. 4 , third image information is shown. When the first image information is generated through the first network function and the second image information is generated through the second network function, third image information may be generated by overlapping the second image information on the first image information. That is, the third image information may relate to a head and neck image in which a fat region is displayed in the head and neck region from which the brain region is removed. In this case, the fat region may be different from other regions in color and transparency, and through this, the fat region may be more easily recognized.

The image information shown in FIG. 4 is exemplary, and various image information may be used according to an embodiment of the present disclosure.

5 is an exemplary view of a disease risk predicted based on a fat mass calculation result according to an embodiment of the present disclosure.

If the amount of fat is calculated through head and neck imaging, it is possible to predict the risk of diseases that are highly correlated with the amount of fat. For example, stages such as normal, low, normal, and risk may be classified according to the amount of fat in the head and neck region, and the risk level for the disease may be predicted based on the classification. At this time, the user's body information may be used together.

Referring to FIG. 5, the amount of fat calculated through the head and neck image is 1529.84 cm ³ , and considering the amount of fat and the user's body information, the user has abdominal fat, sarcopenia, and dyslipidemia. ), and diabetes are low, but the risk of hyperuricemia is extremely high, indicating the need for more detailed examination and treatment.

The disease risk shown in FIG. 5 is an example, and the risk of various diseases can be predicted according to an embodiment of the present disclosure.

6 is a block diagram briefly illustrating the configuration of a fat mass calculating device according to an embodiment of the present disclosure.

The communication unit 610 may receive input data (head and neck MR images, etc.) for fat mass calculation. The communication unit 610 may include a wired/wireless communication unit. When the communication unit 610 includes a wired communication unit, the communication unit 610 may include a local area network (LAN), a wide area network (WAN), a value added network (VAN), and a mobile communication network ( mobile radio communication network), a satellite communication network, and one or more components that enable communication through a mutual combination thereof. In addition, when the communication unit 610 includes a wireless communication unit, the communication unit 610 transmits and receives data or signals wirelessly using cellular communication, a wireless LAN (eg, Wi-Fi), and the like. can In one embodiment, the communication unit 610 may transmit/receive data or signals with an external device or an external server under the control of the processor 640 .

The input unit 620 may receive various user commands through external manipulation. To this end, the input unit 620 may include or connect one or more input devices. For example, the input unit 620 may receive user commands by being connected to various input interfaces such as a keypad and a mouse. To this end, the input unit 620 may include an interface such as a thunderbolt as well as a USB port. In addition, the input unit 620 may receive an external user command by including or combining various input devices such as a touch screen and buttons.

The memory 630 may store programs for operation of the processor 640 and may temporarily or permanently store input/output data. The memory 630 may include a flash memory 630 type, a hard disk type, a multimedia card micro type, or a card type memory 630 (for example, SD or XD memory ( 630), RAM, SRAM, ROM, EEPROM, PROM, magnetic memory 630, a magnetic disk, and an optical disk.

In addition, the memory 630 may store various network functions and algorithms, and may store various data, programs (one or more instructions), applications, software, commands, codes, etc. for driving and controlling the device.

The processor 640 may control the overall operation of the device. Processor 640 may execute one or more programs stored in memory 630 . The processor 640 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor 640 on which methods according to the technical idea of the present disclosure are performed.

In an embodiment, the processor 640 acquires an image group including a plurality of 2D images generated corresponding to the continuous volume of the head and neck of the user, and inputs the image group to the learned first network function to obtain the image group. A second image obtained by generating first image information from which at least a part of brain regions in a group is removed, and inputting the first image information to a learned second network function to detect a fat region from the first image information information, and the amount of fat in the head and neck can be calculated from the second image information. However, it is not limited thereto.

A fat mass calculation method according to an embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the present disclosure, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

In addition, the fat mass calculation method according to the disclosed embodiments may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities.

A computer program product may include a S/W program and a computer-readable storage medium in which the S/W program is stored. For example, a computer program product may include a product in the form of a S/W program (eg, a downloadable app) that is distributed electronically through a manufacturer of an electronic device or an electronic marketplace (eg, Google Play Store, App Store). there is. For electronic distribution, at least a part of the S/W program may be stored in a storage medium or temporarily generated. In this case, the storage medium may be a storage medium of a manufacturer's server, an electronic market server, or a relay server temporarily storing SW programs.

A computer program product may include a storage medium of a server or a storage medium of a client device in a system composed of a server and a client device. Alternatively, if there is a third device (eg, a smart phone) that is communicatively connected to the server or the client device, the computer program product may include a storage medium of the third device. Alternatively, the computer program product may include a S/W program itself transmitted from the server to the client device or the third device or from the third device to the client device.

In this case, one of the server, the client device and the third device may execute the computer program product to perform the method according to the disclosed embodiments. Alternatively, two or more of the server, the client device, and the third device may execute the computer program product to implement the method according to the disclosed embodiments in a distributed manner.

For example, a server (eg, a cloud server or an artificial intelligence server) may execute a computer program product stored in the server to control a client device communicatively connected to the server to perform a method according to the disclosed embodiments.

Although the embodiments have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present disclosure defined in the following claims are also within the scope of the present disclosure. belongs to

Claims (10)

As a fat mass calculation method,
obtaining an image group including a plurality of two-dimensional images generated corresponding to the continuous volume of the head and neck of the user;
generating first image information in which at least a part of a brain region is removed from the image group by inputting the image group to a first learned network function;
generating second image information obtained by detecting a fat region from the first image information by inputting the first image information to a learned second network function; and
and calculating an amount of fat in the head and neck region from the second image information. According to claim 1,
The method of claim 1 , wherein the head and neck region includes a region from the head of the user to a second cervical vertebra in the neck region. According to claim 1,
The generating of the first image information is performed by removing a white matter region from among the brain regions. According to claim 1,
The method further comprising generating third image information including the fat region based on the first image information and the second image information. According to claim 1,
The method further comprising estimating the amount of fat in the body from the amount of fat. According to claim 1,
Further comprising the step of predicting the user's disease risk from the fat mass. According to claim 1,
The step of predicting the disease risk is performed by predicting the risk for at least one of abdominal fat, sarcopenia, dyslipidemia, diabetes and hyperuricemia , Way. According to claim 1,
The method further comprises acquiring body information of the user, wherein the body information includes the user's height, weight and past medical history. In the fat mass calculation device,
a memory for storing a program for calculating fat mass; and
By executing the program, an image group including a plurality of 2-dimensional images generated corresponding to the continuous volume of the user's head and neck is obtained, and the image group is input to the learned first network function to generate brain data from the image group. First image information from which at least a part of the (brain) region is removed is generated, and the first image information is input to the learned second network function to generate second image information obtained by detecting a fat region from the first image information and at least one processor configured to calculate the amount of fat in the head and neck region from the second image information. A computer program stored in a recording medium to execute the method of any one of claims 1 to 8.

Images